Measuring change over time: assessing the usefulness of evaluative instruments

Abstract

Reliability, the ratio of the variance attributable to true differences among subjects to the total variance, is an important attribute of psychometric measures. However, it is possible for instruments to be reliable, but unresponsive to change; conversely, they may show poor reliability but excellent responsiveness. This is especially true for instruments in which items are tailored to the individual respondent. Therefore, we suggest a new index of responsiveness to assess the usefulness of instruments designed to measure change over time. This statistic, which relates the minimal clinically important difference to the variability in stable subjects, has direct sample size implications. Responsiveness should join reliability and validity as necessary requirements for instruments designed primarily to measure change over time.